Learning to Advise and Learning from Advice in Cooperative Multi-Agent Reinforcement Learning

TL;DR

This paper introduces LALA, a hierarchical advice-based framework for multi-agent reinforcement learning that improves coordination and learning efficiency by leveraging spatiotemporal decision structures and multilevel emergence dynamics.

Contribution

It proposes a novel hierarchical advice mechanism with a spatiotemporal neural network and policy discriminator, addressing coordination hierarchy in MARL.

Findings

LALA outperforms baseline methods in learning efficiency.

LALA enhances coordination capabilities in multi-agent systems.

The approach offers a new perspective on analyzing MARL through emergence dynamics.

Abstract

Learning to coordinate is a daunting problem in multi-agent reinforcement learning (MARL). Previous works have explored it from many facets, including cognition between agents, credit assignment, communication, expert demonstration, etc. However, less attention were paid to agents' decision structure and the hierarchy of coordination. In this paper, we explore the spatiotemporal structure of agents' decisions and consider the hierarchy of coordination from the perspective of multilevel emergence dynamics, based on which a novel approach, Learning to Advise and Learning from Advice (LALA), is proposed to improve MARL. Specifically, by distinguishing the hierarchy of coordination, we propose to enhance decision coordination at meso level with an advisor and leverage a policy discriminator to advise agents' learning at micro level. The advisor learns to aggregate decision information in both spatial and temporal domains and generates coordinated decisions by employing a spatiotemporal dual graph convolutional neural network with a task-oriented objective function. Each agent learns from the advice via a policy generative adversarial learning method where a discriminator distinguishes between the policies of the agent and the advisor and boosts both of them based on its judgement. Experimental results indicate the advantage of LALA over baseline approaches in terms of both learning efficiency and coordination capability. Coordination mechanism is investigated from the perspective of multilevel emergence dynamics and mutual information point of view, which provides a novel perspective and method to analyze and improve MARL algorithms.